© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 89541
    Prev
    Next
    INDEX
    Explanations

    code/data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     그리고
    -0.07
     wiped
    -0.07
    物质
    -0.07
    _SWAP
    -0.07
    ษา
    -0.07
    菜单
    -0.07
     $('.
    -0.07
    られ
    -0.07
    /xml
    -0.07
     ..."↵↵
    -0.06
    POSITIVE LOGITS
    _gate
    0.07
     theat
    0.07
    Combat
    0.07
    (jScrollPane
    0.07
     disput
    0.07
    מתח
    0.07
    再也不
    0.07
    霎
    0.06
     infield
    0.06
    擂
    0.06
    Activations Density 0.013%

    No Known Activations